College of Computer Science and Mathematics

Master Dissertation Final DefenseDiscussion of a master’s thesis in the College of Computer Science and Mathematics – Software DepartmentEntitled (Design a tool forsoftware effort estimationbased on machine learning)In continuation of the movement of scientific research and in the presence of the esteemed President of the University of Mosul, Prof. Dr. Qusay Kamal Al-Din Al-Ahmadi, and the presence and follow-up of the respected Mrs. Dean of the College of Computer Science and Mathematics, Prof. Dr. Duha Bashir Abdullah, the esteemedOn Tuesday 25/10/2022, the College of Computer Science and Mathematics at the University of Mosul discussed a master’s thesis for the student (Farah Basil Ahmed Thanoun), under the supervision of Prof. Dr..Laheeb Mohamed Ibrahim.The thesis submitted by the student dealt with the design of a tool for estimating software effort using machine learningThe study dealt with the construction and development of EE_Tool to estimate effort to help project engineers and managers to estimate effort using machine learning algorithm Random Forest RF and deep learning models (artificial neural network Long short term memory LSTM, artificial neural network long memory Stacked Long short Term Memory Stacked _LSTM, Artificial Neural Network Bidirectional Long Short Term Memory Bi_LSTM) with five datasets (china, Albrecht, Maxwell, Desharnais, Kitchenham), in which a series of manipulations were first performed Pre-existing data and its normalization process and then choosing the features that have the strongest correlation with the real effort to reduce time and increase the efficiency of the tool models, and then predict the effort using the tool models, and then calculate the evaluation metrics (MAE, RMSE, MSE, R _Squared, MRE) based on the effort Estimator, real effort, comparison between models and highlighting the best among them for each data set. The tool’s models were compared with four models of S’s work. According to the evaluation metrics, we found that the LSTM and Bi_LSTM models were the best in estimating the effort.The study aims to design a tool to estimate the effort needed to develop software projects using the Random Forest RF machine learning algorithm and deep learning models that helps get results as close to real effort as possible to help software engineers and managers come up with an approximation of Actualeffort early in the life cycle Software development to facilitate the development process and help its success.The scientific committee included the following members:

• Associate Prof. Dr. NajlaAkram AL-Saati (University of Mosul)/ Chief
• Associate Prof. Dr. Mohammed Abd- Almuttalib Mohammed (University of Nineveh)/ Member
• Naktal Moayed Edan (University of Mosul)/ Member
• Dr. Laheeb Mohammed Ibrahim (University of Mosul)Supervisor and Member Congratulations Farah , we hope you all the best